High-Accuracy and Efficient Classification of Uranium Slag by Origin and Category via LIBS Integrated with Hybrid Machine Learning
Open Access
Abstract
Accurate classification of uranium slag origin and category is essential for nuclear environmental monitoring and safety. This study presents a hybrid framework combining laser-induced breakdown spectroscopy (LIBS), four preprocessing methods, and five machine learning algorithms for rapid uranium slag classification. A total of nine sample categories were collected from three mining areas, with categories defined by their U concentration levels within each origin. Standard normal variate (SNV), Savitzky–Golay smoothing (SG), and their combinations (SNV-SG, SG-SNV) were applied to evaluate preprocessing effects. To address ultra-high-dimensional spectral data (49,242 points per spectrum), principal component analysis (PCA) and random forest (RF) were employed for feature engineering, integrated with support vector machine (SVM), linear discriminant analysis (LDA), and K-nearest neighbors (KNN) classifiers. Hyperparameter optimization via five-fold cross-validation and Bayesian optimization enhanced accuracy and efficiency. RF-based hybrid models consistently outperformed PCA-based counterparts. Remarkably, the RF-LDA model with SNV-SG preprocessing achieved 100% classification accuracy across all test sets with a processing time of only 10.46 s, demonstrating exceptional discriminative power and computational efficiency. These findings establish that combining RF feature selection with advanced machine learning offers a robust solution for LIBS-based nuclear material classification, with significant implications for both nuclear safety and resource management.Keywords
Funding Information
- National Natural Science Foundation of China (12365021, 12005037)
- Natural Science Foundation of Jiangxi Province (20224BAB201021, 20242BAB26038)
This publication has 38 references indexed in Scilit:
- Quantitative analysis and classification of uranium polymetallic ores using femtosecond laser-induced breakdown spectroscopy combined with machine learning algorithmsApplied Physics B, 2025
- A review of machine learning applications for identification and classification problems in paleontologyEcological Informatics, 2025
- Efficient and anti-interference plastic classification method suitable for one-shot learning based on laser induced breakdown spectroscopyChemosphere, 2025
- Radiological considerations in using uranium mine waste rock for road construction materialsJournal of Environmental Radioactivity, 2025
- Machine learning in laser-induced breakdown spectroscopy: A reviewFrontiers of Physics, 2024
- Exploring Machine-Learning-Enabled Libs Towards Forensic Trace Attributive Analysis of Fission Products in Surrogate High-Level Nuclear WasteJournal of Applied Spectroscopy, 2024
- Fingerprinting black tea: When spectroscopy meets machine learning a novel workflow for geographical origin identificationFood Chemistry, 2023
- Geochemical identification and classification of cherts using handheld laser induced breakdown spectroscopy (LIBS) supported by supervised machine learning algorithmsApplied Geochemistry, 2023
- A hybrid feature selection combining wavelet transform for quantitative analysis of heat value of coal using laser-induced breakdown spectroscopyApplied Physics B, 2021
- Identification and classification of explosives using semi-supervised learning and laser-induced breakdown spectroscopyJournal of Hazardous Materials, 2019